地震多属性分析技术在煤层厚度预测中的应用分析  

Application of seismic multi-attribute analysis technique in coal seam thickness prediction

作　　者：单蕊 SHAN Rui(Xi'an Research Institute, China Coal Technology & Engineering Group Corp., Xi'an 710077, China)

机构地区：[1]中煤科工集团西安研究院有限公司,西安710077

出　　处：《物探化探计算技术》2021年第3期304-310,共7页Computing Techniques For Geophysical and Geochemical Exploration

基　　金：中煤科工集团西安研究院有限公司科技创新(2019XAYMS28)。

摘　　要：准确预测煤层厚度对指导煤矿安全生产具有重要意义。以新疆某三维勘探研究区A3煤层的煤层厚度预测为实例,选择15口井作为样本数据,通过提取目的层地震属性特征,应用多元回归分析方法和神经网络方法进行煤层厚度预测,煤层厚度预测趋势的相关系数高达0.98。预测结果表明,多属性定量预测煤层厚度是一种有效的方法,神经网络方法得到的煤层厚度预测值较多元回归方法更为准确。Accurate prediction of coal thickness is of great significance to guide coal mine safety production.Through the extraction of seismic attribute characteristics of reflected wave in the target layer of a high-density three-dimensional exploration and in-depth analysis were applied for the research area in Xinjiang.Multiple regression analysis method and neural network method were applied to predict coal thickness using the sample data selected from 15Wells.The correlation coefficient of coal seam thickness prediction trend was 0.98.The prediction results show that the quantitative prediction of coal seam thickness is an effective method.The neural network method is more accurate than the multiple regression one in calculating the thickness of coal seam.

关 键 词：煤层厚度预测 地震属性 多元回归分析 神经网络 

分 类 号：P631.4[天文地球—地质矿产勘探]